all AI news
Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
March 1, 2024, 5:49 a.m. | Nan Xu, Fei Wang, Ben Zhou, Bang Zheng Li, Chaowei Xiao, Muhao Chen
cs.CL updates on arXiv.org arxiv.org
Abstract: While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after safety alignment. In this paper, we investigate a novel category of jailbreak attacks specifically designed to target the cognitive structure and processes of LLMs. Specifically, we analyze the safety vulnerability of LLMs in the face of (1) multilingual cognitive overload, …
abstract alignment arxiv attacks cognitive cs.cl jailbreak jailbreaking language language models large language large language models llms novel overload paper power responses safety thinking type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US